linkedin-article-publisher

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill explicitly navigates to and inspects LinkedIn's public article editor (browser_navigate: https://www.linkedin.com/article/new/ and subsequent browser_snapshot/browser_click operations) and thus consumes untrusted, user-generated third‑party web content (LinkedIn) as part of its runtime workflow, which could enable indirect prompt injection.